Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2765 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.8761. Min Range: -1.8761

Max Act: 1.8761. Min Act: -0.0000

Data Index: 1490759 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.5269. Min Act: -0.0000

Data Index: 76870 (The Pile)

Max Activating Token Index: 274

Text #2

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.3698. Min Act: 0.0000

Data Index: 318569 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.3093. Min Act: -0.0000

Data Index: 792121 (The Pile)

Max Activating Token Index: 649

Text #4

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.3140. Min Act: -0.0000

Data Index: 1816946 (The Pile)

Max Activating Token Index: 679

Text #5

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.1290. Min Act: -0.0000

Data Index: 100800 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.3078. Min Act: -0.0000

Data Index: 1480114 (The Pile)

Max Activating Token Index: 194

Text #7

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2832. Min Act: -0.0000

Data Index: 1689026 (The Pile)

Max Activating Token Index: 165

Text #8

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2522. Min Act: -0.0000

Data Index: 245086 (The Pile)

Max Activating Token Index: 66

Text #9

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2416. Min Act: -0.0000

Data Index: 1462808 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2362. Min Act: -0.0000

Data Index: 662972 (The Pile)

Max Activating Token Index: 978

Text #11

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2352. Min Act: -0.0000

Data Index: 1001729 (The Pile)

Max Activating Token Index: 193

Text #12

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2164. Min Act: -0.0000

Data Index: 855423 (The Pile)

Max Activating Token Index: 974

Text #13

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.3769. Min Act: -0.0000

Data Index: 1834714 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1633395 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2319. Min Act: 0.0000

Data Index: 1064871 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2219. Min Act: -0.0000

Data Index: 471055 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.1943. Min Act: -0.0000

Data Index: 279448 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.2025. Min Act: -0.0000

Data Index: 1756660 (The Pile)

Max Activating Token Index: 899

Text #19

Max Range: 1.8761. Min Range: -1.8761

Max Act: 0.1911. Min Act: -0.0000

Data Index: 843630 (The Pile)

Max Activating Token Index: 495